print(f"{time.time() - currtime:.3f} elapsed to scale and center data.")
X_test = scaler.transform(X_test)
#%%
np.random.seed(seed)
currtime = time.time()
pca = PCA(n_components=n_components)
X_train_pca = pca.fit_transform(X_train)
print(f"{time.time() - currtime:.3f} elapsed to fit PCA model.")
X_test_pca = pca.transform(X_test)
#%%
np.random.seed(seed + 2)
currtime = time.time()
sca = SparseComponentAnalysis(n_components=n_components,
max_iter=30,
gamma=50,
verbose=10)
X_train_sca = sca.fit_transform(X_train)
print(f"{time.time() - currtime:.3f} elapsed for SCA.")
X_test_sca = sca.transform(X_test)
#%%
neuron_types = sequencing_df.index.get_level_values("Neuron_type").values
neuron_type_palette = dict(zip(np.unique(neuron_types), cc.glasbey_light))
y_train = index_train.get_level_values(level="Neuron_type").values
y_test = index_test.get_level_values(level="Neuron_type").values
pg = pairplot(X_train_sca[:, :4],
labels=y_train,
palette=neuron_type_palette,
method = "PCA"
else:
method = "SCA"
print(
f"method = {method}, n_components = {n_components}, gamma = {gamma}"
)
print()
curr_params = (method, n_components, gamma)
params.append(curr_params)
# fit model
currtime = time.time()
model = SparseComponentAnalysis(
n_components=n_components,
max_iter=max_iter,
gamma=gamma,
verbose=10,
tol=tol,
)
S_train = model.fit_transform(X_train)
train_time = time.time() - currtime
print(f"{train_time:.3f} elapsed to train model.")
S_test = model.transform(X_test)
# save model fit
models_by_params[curr_params] = model
S_train_by_params[curr_params] = S_train
S_test_by_params[curr_params] = S_test
# save metrics
#%%
U_thresh = soft_threshold(U_rot, gamma=100)
pairplot(U_thresh, alpha=0.2)
#%%
#%%
currtime = time.time()
pca = PCA(n_components=n_components)
X_pca = pca.fit_transform(X_train)
print(f"{time.time() - currtime:.3f} elapsed to fit PCA model.")
#%%
currtime = time.time()
sca = SparseComponentAnalysis(n_components=n_components, max_iter=max_iter, gamma=gamma)
X_sca = sca.fit_transform(X_train)
print(f"{time.time() - currtime:.3f} elapsed to fit SCA model.")
#%%
max_iter = 5
gammas = [n_components, 100, 500, np.sqrt(X_train.shape[1]) * n_components, np.inf]
models_by_gamma = {}
Xs_by_gamma = {}
for i, gamma in enumerate(gammas):
print(f"Gamma = {gamma}...")
if gamma == np.inf:
_max_iter = 0
else:
_max_iter = max_iter
currtime = time.time()
center = True
scale = False
max_iter = 1
k_range = np.arange(2, d + 1, 4)
n_replicates = 400
rows = []
for i in range(n_replicates):
X = sample_data()
if center:
X -= np.mean(X, axis=0)
for k in k_range:
gamma = k * 2.5
sca = SparseComponentAnalysis(n_components=k,
gamma=gamma,
max_iter=max_iter,
tol=0)
Z_hat_sca = sca.fit_transform(X)
Y_hat_sca = sca.components_.T
pve = proportion_variance_explained(X, Y_hat_sca)
rows.append({
"replicate": i,
"k": k,
"pve": pve,
"method": "SCA",
"n_nonzero": np.count_nonzero(Y_hat_sca),
})
Z_hat_r, Y_hat_r, outs = sca_R(
X,
# 500,
# int(np.sqrt(X_train.shape[1]) * n_components),
np.inf,
]
gammas = [float(g) for g in gammas]
models_by_gamma = {}
Xs_by_gamma = {}
for i, gamma in enumerate(gammas):
print(f"Gamma = {gamma}...")
if gamma == np.inf:
_max_iter = 0
else:
_max_iter = max_iter
currtime = time.time()
sca = SparseComponentAnalysis(n_components=n_components,
max_iter=_max_iter,
gamma=gamma,
verbose=10)
X_sca = sca.fit_transform(X_train)
print(f"{time.time() - currtime:.3f} elapsed.")
models_by_gamma[gamma] = sca
Xs_by_gamma[gamma] = X_sca
print()
#%%
rows = []
for gamma, model in models_by_gamma.items():
explained_variance_ratio = model.explained_variance_ratio_
for k, ev in enumerate(explained_variance_ratio):
n_nonzero = np.count_nonzero(model.components_[:k + 1])
rows.append({